com.johnsnowlabs.nlp.annotators.chunker
ChunkSentenceSplitter
Companion object ChunkSentenceSplitter
class ChunkSentenceSplitter extends AnnotatorModel[ChunkSentenceSplitter] with HasSimpleAnnotate[ChunkSentenceSplitter] with CheckLicense
An annotator that splits a document into sentences based on provided chunks. The first piece of the document is treated as a header, and subsequent chunks are labeled with their associated entities.
This annotator is particularly useful when identifying titles and subtitles using Named Entity Recognition (NER), followed by a paragraph-level split.
Example
// Create a DataFrame with a "text" column val data = Seq(text, text).toDS.toDF("text") // Set up the NLP pipeline with DocumentAssembler, RegexMatcher, and ChunkSentenceSplitter val documentAssembler = new DocumentAssembler().setInputCol("text").setOutputCol("doc") val regexMatcher = new RegexMatcher().setInputCols("doc").setOutputCol("chunks") .setExternalRules("src/test/resources/chunker/title_regex.txt", ",") val chunkSentenceSplitter = new ChunkSentenceSplitter().setInputCols("chunks", "doc").setOutputCol("paragraphs") val pipeline = new Pipeline().setStages(Array(documentAssembler, regexMatcher, chunkSentenceSplitter)) // Fit the pipeline to the data and transform it val result = pipeline.fit(data).transform(data).select("paragraphs") result.show(truncate = false)
- Grouped
- Alphabetic
- By Inheritance
- ChunkSentenceSplitter
- CheckLicense
- HasSimpleAnnotate
- AnnotatorModel
- CanBeLazy
- RawAnnotator
- HasOutputAnnotationCol
- HasInputAnnotationCols
- HasOutputAnnotatorType
- ParamsAndFeaturesWritable
- HasFeatures
- DefaultParamsWritable
- MLWritable
- Model
- Transformer
- PipelineStage
- Logging
- Params
- Serializable
- Serializable
- Identifiable
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Instance Constructors
Type Members
Value Members
-
final
def
!=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
##(): Int
- Definition Classes
- AnyRef → Any
-
final
def
$[T](param: Param[T]): T
- Attributes
- protected
- Definition Classes
- Params
-
def
$$[T](feature: StructFeature[T]): T
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
$$[K, V](feature: MapFeature[K, V]): Map[K, V]
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
$$[T](feature: SetFeature[T]): Set[T]
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
$$[T](feature: ArrayFeature[T]): Array[T]
- Attributes
- protected
- Definition Classes
- HasFeatures
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
_transform(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): DataFrame
- Attributes
- protected
- Definition Classes
- AnnotatorModel
-
def
afterAnnotate(dataset: DataFrame): DataFrame
- Attributes
- protected
- Definition Classes
- AnnotatorModel
-
def
annotate(annotations: Seq[Annotation]): Seq[Annotation]
- annotations
a Sequence of chunks to transform
- returns
a Sequence of Merged CHUNK Annotations
- Definition Classes
- ChunkSentenceSplitter → HasSimpleAnnotate
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
beforeAnnotate(dataset: Dataset[_]): Dataset[_]
- Attributes
- protected
- Definition Classes
- AnnotatorModel
-
final
def
checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
- Attributes
- protected
- Definition Classes
- HasInputAnnotationCols
-
def
checkValidEnvironment(spark: Option[SparkSession], scopes: Seq[String]): Unit
- Definition Classes
- CheckLicense
-
def
checkValidScope(scope: String): Unit
- Definition Classes
- CheckLicense
-
def
checkValidScopeAndEnvironment(scope: String, spark: Option[SparkSession], checkLp: Boolean): Unit
- Definition Classes
- CheckLicense
-
def
checkValidScopesAndEnvironment(scopes: Seq[String], spark: Option[SparkSession], checkLp: Boolean): Unit
- Definition Classes
- CheckLicense
-
final
def
clear(param: Param[_]): ChunkSentenceSplitter.this.type
- Definition Classes
- Params
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
def
copy(extra: ParamMap): ChunkSentenceSplitter
- Definition Classes
- RawAnnotator → Model → Transformer → PipelineStage → Params
-
def
copyValues[T <: Params](to: T, extra: ParamMap): T
- Attributes
- protected
- Definition Classes
- Params
-
final
def
defaultCopy[T <: Params](extra: ParamMap): T
- Attributes
- protected
- Definition Classes
- Params
-
val
defaultEntity: Param[String]
String parameter representing the default name for the entity assigned to content between the start of the document and the first labeled chunk.
String parameter representing the default name for the entity assigned to content between the start of the document and the first labeled chunk.
- Note
Default: introduction
-
def
dfAnnotate: UserDefinedFunction
- Definition Classes
- HasSimpleAnnotate
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
equals(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
explainParam(param: Param[_]): String
- Definition Classes
- Params
-
def
explainParams(): String
- Definition Classes
- Params
-
def
extraValidate(structType: StructType): Boolean
- Attributes
- protected
- Definition Classes
- RawAnnotator
-
def
extraValidateMsg: String
- Attributes
- protected
- Definition Classes
- RawAnnotator
-
final
def
extractParamMap(): ParamMap
- Definition Classes
- Params
-
final
def
extractParamMap(extra: ParamMap): ParamMap
- Definition Classes
- Params
-
val
features: ArrayBuffer[Feature[_, _, _]]
- Definition Classes
- HasFeatures
-
def
finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
def
get[T](feature: StructFeature[T]): Option[T]
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
get[T](feature: SetFeature[T]): Option[Set[T]]
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
get[T](feature: ArrayFeature[T]): Option[Array[T]]
- Attributes
- protected
- Definition Classes
- HasFeatures
-
final
def
get[T](param: Param[T]): Option[T]
- Definition Classes
- Params
- def getChunksEntitiesBySentence(annotations: Seq[Annotation]): Seq[Seq[Annotation]]
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
final
def
getDefault[T](param: Param[T]): Option[T]
- Definition Classes
- Params
- def getDefaultEntity(): String
- def getGroupBySentences(): Boolean
-
def
getInputCols: Array[String]
- Definition Classes
- HasInputAnnotationCols
- def getInsertChunk(): Boolean
-
def
getLazyAnnotator: Boolean
- Definition Classes
- CanBeLazy
-
final
def
getOrDefault[T](param: Param[T]): T
- Definition Classes
- Params
-
final
def
getOutputCol: String
- Definition Classes
- HasOutputAnnotationCol
-
def
getParam(paramName: String): Param[Any]
- Definition Classes
- Params
-
val
groupBySentences: BooleanParam
This parameter determines whether to split a document into paragraphs by grouping chunks by sentences.
This parameter determines whether to split a document into paragraphs by grouping chunks by sentences. If set to false, it assumes a single document annotation for all chunks. Set to true if you want to group chunks by sentences, and the input column of your chunk annotator is generated by a sentence detector.
- Note
Default: true
-
final
def
hasDefault[T](param: Param[T]): Boolean
- Definition Classes
- Params
-
def
hasParam(paramName: String): Boolean
- Definition Classes
- Params
-
def
hasParent: Boolean
- Definition Classes
- Model
-
def
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
- Attributes
- protected
- Definition Classes
- Logging
-
def
initializeLogIfNecessary(isInterpreter: Boolean): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
val
inputAnnotatorTypes: Array[AnnotatorType]
Input annotator types: DOCUMENT,CHUNK
Input annotator types: DOCUMENT,CHUNK
- Definition Classes
- ChunkSentenceSplitter → HasInputAnnotationCols
-
final
val
inputCols: StringArrayParam
- Attributes
- protected
- Definition Classes
- HasInputAnnotationCols
-
val
insertChunk: BooleanParam
Boolean parameter that determines whether to include the chunk in the resulting sentences or not.
Boolean parameter that determines whether to include the chunk in the resulting sentences or not.
When
insertChunk
is set to true, the chunk will be added to the generated sentences. If set to false, the chunk will be omitted from the sentences.- Note
Default: true
-
final
def
isDefined(param: Param[_]): Boolean
- Definition Classes
- Params
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
-
final
def
isSet(param: Param[_]): Boolean
- Definition Classes
- Params
-
def
isTraceEnabled(): Boolean
- Attributes
- protected
- Definition Classes
- Logging
-
val
lazyAnnotator: BooleanParam
- Definition Classes
- CanBeLazy
-
def
log: Logger
- Attributes
- protected
- Definition Classes
- Logging
-
def
logDebug(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logDebug(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logError(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logError(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logInfo(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logInfo(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logName: String
- Attributes
- protected
- Definition Classes
- Logging
-
def
logTrace(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logTrace(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logWarning(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logWarning(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
msgHelper(schema: StructType): String
- Attributes
- protected
- Definition Classes
- HasInputAnnotationCols
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
def
onWrite(path: String, spark: SparkSession): Unit
- Attributes
- protected
- Definition Classes
- ParamsAndFeaturesWritable
-
val
optionalInputAnnotatorTypes: Array[String]
- Definition Classes
- HasInputAnnotationCols
-
val
outputAnnotatorType: AnnotatorType
Output annotator types: CHUNK
Output annotator types: CHUNK
- Definition Classes
- ChunkSentenceSplitter → HasOutputAnnotatorType
-
final
val
outputCol: Param[String]
- Attributes
- protected
- Definition Classes
- HasOutputAnnotationCol
-
lazy val
params: Array[Param[_]]
- Definition Classes
- Params
-
var
parent: Estimator[ChunkSentenceSplitter]
- Definition Classes
- Model
-
def
save(path: String): Unit
- Definition Classes
- MLWritable
- Annotations
- @Since( "1.6.0" ) @throws( ... )
-
def
set[T](feature: StructFeature[T], value: T): ChunkSentenceSplitter.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[K, V](feature: MapFeature[K, V], value: Map[K, V]): ChunkSentenceSplitter.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[T](feature: SetFeature[T], value: Set[T]): ChunkSentenceSplitter.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
set[T](feature: ArrayFeature[T], value: Array[T]): ChunkSentenceSplitter.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
final
def
set(paramPair: ParamPair[_]): ChunkSentenceSplitter.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
set(param: String, value: Any): ChunkSentenceSplitter.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
set[T](param: Param[T], value: T): ChunkSentenceSplitter.this.type
- Definition Classes
- Params
-
def
setDefault[T](feature: StructFeature[T], value: () ⇒ T): ChunkSentenceSplitter.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): ChunkSentenceSplitter.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): ChunkSentenceSplitter.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
def
setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): ChunkSentenceSplitter.this.type
- Attributes
- protected
- Definition Classes
- HasFeatures
-
final
def
setDefault(paramPairs: ParamPair[_]*): ChunkSentenceSplitter.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
setDefault[T](param: Param[T], value: T): ChunkSentenceSplitter.this.type
- Attributes
- protected[org.apache.spark.ml]
- Definition Classes
- Params
-
def
setDefaultEntity(value: String): ChunkSentenceSplitter.this.type
Sets defaultEntity, defining the default name for the entity that represents content between the beginning of the document and the first chunk.
Sets defaultEntity, defining the default name for the entity that represents content between the beginning of the document and the first chunk.
- returns
This instance with the updated initEntityName property.
- Note
Default: introduction
-
def
setGroupBySentences(value: Boolean): ChunkSentenceSplitter.this.type
Sets groupBySentences, which determines whether to split a document into paragraphs by grouping chunks by sentences.
Sets groupBySentences, which determines whether to split a document into paragraphs by grouping chunks by sentences. If set to false, it assumes a single document annotation for all chunks. Set to true if you want to group chunks by sentences, and the input column of your chunk annotator is generated by a sentence detector.
- returns
This instance with the updated groupBySentences property.
- Note
Default: true
-
final
def
setInputCols(value: String*): ChunkSentenceSplitter.this.type
- Definition Classes
- HasInputAnnotationCols
-
def
setInputCols(value: Array[String]): ChunkSentenceSplitter.this.type
- Definition Classes
- HasInputAnnotationCols
-
def
setInsertChunk(value: Boolean): ChunkSentenceSplitter.this.type
Sets the value for the
insertChunk
parameter, determining whether to include the chunk in the resulting sentences or not.Sets the value for the
insertChunk
parameter, determining whether to include the chunk in the resulting sentences or not.When
insertChunk
is set to true, the chunk will be added to the generated sentences. If set to false, the chunk will be omitted from the sentences.- returns
This instance with the updated
insertChunk
property.
- Note
Default: true
-
def
setLazyAnnotator(value: Boolean): ChunkSentenceSplitter.this.type
- Definition Classes
- CanBeLazy
-
final
def
setOutputCol(value: String): ChunkSentenceSplitter.this.type
- Definition Classes
- HasOutputAnnotationCol
-
def
setParent(parent: Estimator[ChunkSentenceSplitter]): ChunkSentenceSplitter
- Definition Classes
- Model
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toString(): String
- Definition Classes
- Identifiable → AnyRef → Any
-
final
def
transform(dataset: Dataset[_]): DataFrame
- Definition Classes
- AnnotatorModel → Transformer
-
def
transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
- Definition Classes
- Transformer
- Annotations
- @Since( "2.0.0" )
-
def
transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
- Definition Classes
- Transformer
- Annotations
- @Since( "2.0.0" ) @varargs()
-
final
def
transformSchema(schema: StructType): StructType
- Definition Classes
- RawAnnotator → PipelineStage
-
def
transformSchema(schema: StructType, logging: Boolean): StructType
- Attributes
- protected
- Definition Classes
- PipelineStage
- Annotations
- @DeveloperApi()
-
val
uid: String
- Definition Classes
- ChunkSentenceSplitter → Identifiable
-
def
validate(schema: StructType): Boolean
- Attributes
- protected
- Definition Classes
- RawAnnotator
-
final
def
wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
def
wrapColumnMetadata(col: Column): Column
- Attributes
- protected
- Definition Classes
- RawAnnotator
-
def
write: MLWriter
- Definition Classes
- ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable
Inherited from CheckLicense
Inherited from HasSimpleAnnotate[ChunkSentenceSplitter]
Inherited from AnnotatorModel[ChunkSentenceSplitter]
Inherited from CanBeLazy
Inherited from RawAnnotator[ChunkSentenceSplitter]
Inherited from HasOutputAnnotationCol
Inherited from HasInputAnnotationCols
Inherited from HasOutputAnnotatorType
Inherited from ParamsAndFeaturesWritable
Inherited from HasFeatures
Inherited from DefaultParamsWritable
Inherited from MLWritable
Inherited from Model[ChunkSentenceSplitter]
Inherited from Transformer
Inherited from PipelineStage
Inherited from Logging
Inherited from Params
Inherited from Serializable
Inherited from Serializable
Inherited from Identifiable
Inherited from AnyRef
Inherited from Any
Parameters
Annotator types
Required input and expected output annotator types